crawlette 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 88877d0289d6126cd7b340ce741db5da6c40ac3e
+  data.tar.gz: 08e58934ae52afcce2f5c7ab371f9ac55cfd5bfa
+SHA512:
+  metadata.gz: 06571be5090c0e02d374fb01f89c07f377761c498ff72ff28b437d6a97da7440baa3cd891230281554f21391839848e7761fa236f9af0154b96813325a117b06
+  data.tar.gz: 3f03a72370cdce93f983a633f57229132ee55fc8ae254fbfa3f89ef6310b10b2b24cfda848088042dc5f8554b67163a873b3d1a209407da624690552c9fe5da1

data/.gitignore

@@ -0,0 +1,14 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--format documentation

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in crawlette.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Miguel Camba
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,11 @@
+# Crawlette
+
+Very simple command line utility to crawl an URL and show the links and assets of each page.
+
+## Installation
+
+    $ gem install crawlette
+
+## Usage
+
+    $ crawlette http://miguelcamba.com

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/bin/crawlette

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+lib = File.expand_path(File.dirname(__FILE__) + '/../lib')
+$LOAD_PATH.unshift(lib) if File.directory?(lib) && !$LOAD_PATH.include?(lib)
+
+require 'awesome_print'
+require 'crawlette'
+ap Crawlette::Crawler.new(ARGV[0]).crawl

data/crawlette.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'crawlette/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "crawlette"
+  spec.version       = Crawlette::VERSION
+  spec.authors       = ["Miguel Camba"]
+  spec.email         = ["miguel.camba@gmail.com"]
+  spec.summary       = %q{Very simple web crawler}
+  spec.description   = %q{Crawls a page, with no limits and without visiting external domains}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency "nokogiri", '~> 1.6'
+  spec.add_runtime_dependency "awesome_print", '~> 1.2'
+  spec.add_development_dependency "bundler", "~> 1.6"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.1"
+end

data/lib/crawlette.rb

@@ -0,0 +1,2 @@
+require "crawlette/version"
+require "crawlette/crawler"

data/lib/crawlette/crawler.rb

@@ -0,0 +1,77 @@
+require 'uri'
+require 'net/http'
+require 'crawlette/page'
+
+module Crawlette
+  class Crawler
+    MAX_THREADS = 8
+    BadUrlError = Class.new(ArgumentError)
+
+    def initialize(url, sitemap = {})
+      @uri = URI.parse(url)
+      @pending_uris = [@uri]
+      @sitemap = sitemap
+      unless @uri.host && @uri.scheme
+        fail BadUrlError, "Invalid url: You must provide a full qualified url"
+      end
+    end
+
+
+    # Crawl a web page and generate a sitemap that must also contain:
+    #
+    # * Links betwenn pages.
+    # * On which static assets each page depend on.
+    #
+    # Example:
+    #
+    # Crawlette::Crawler.new('https://gocardless.com').crawl
+    # # => {
+    #   'http://example.com/' => {
+    #     'assets' => ['http://example.com/image1.png', 'http://example.com/script1.js', 'http://example.com/stylesheet1.css'],
+    #     'links' => ['http://example.com/watch-a-demo', 'http://example.com/features'],
+    #   },
+    #   'http://example.com/watch-a-demo' => {
+    #     'assets' => ['http://example.com/image2.png', 'http://example.com/script2.js', 'http://example.com/stylesheet2.css'],
+    #     'links' => ['http://example.com/whatever1', 'http://example.com/whatever2'],
+    #   },
+    #   'http://example.com/features' => {
+    #     'assets' => ['http://example.com/image3.png', 'http://example.com/script3.js', 'http://example.com/stylesheet3.css'],
+    #     'links' => ['http://example.com/features/api', 'http://example.com/features/pricing'],
+    #   },
+    #   'http://example.com/features/api' => {
+    #     ...
+    #   },
+    #   'http://example.com/features/pricing' => {
+    #     ...
+    #   },
+    # }
+
+    def crawl
+      while @pending_uris.size > 0
+        threads = []
+        @pending_uris.pop(MAX_THREADS).each do |uri|
+          threads << Thread.new do
+            process_uri(uri)
+          end
+        end
+        threads.each(&:join)
+      end
+      @sitemap
+    end
+
+
+    private
+
+    def process_uri(uri)
+      @sitemap[uri.to_s] ||= begin
+        puts "... Fetching #{uri.to_s}"
+        page = Page.new(Net::HTTP.get(uri), uri)
+        more_uris = page.links.map { |url| URI.parse(url) }
+        @pending_uris.push(*more_uris)
+        { 'links'  => page.links, 'assets' => page.assets }
+      end
+    rescue => e
+      puts "ERROR! Cannot fetch #{@uri}: #{e.message}"
+    end
+  end
+end

data/lib/crawlette/page.rb

@@ -0,0 +1,43 @@
+require 'nokogiri'
+
+module Crawlette
+  class Page
+    MAILTO_REGEX = /^mailto:/
+    attr_reader :uri
+
+    def initialize(html, uri)
+      @html = html
+      @uri  = uri
+    end
+
+    def links
+      @links ||= sanitize_urls(document.css('a[href]').map { |a| a["href"] })
+    end
+
+    def assets
+      @assets ||= begin
+        urls = document.css('[src]').map { |a| a["src"] }
+        urls += document.css('link[rel="stylesheet"][href]').map { |a| a["href"] }
+        urls += document.css('meta[name^="og:image"]').map { |a| a["content"] }
+
+        sanitize_urls(urls, external_links: true)
+      end
+    end
+
+    private
+
+    def document
+      @document ||= Nokogiri::HTML.parse(@html)
+    end
+
+    def sanitize_urls(urls, external_links: false)
+      urls.reject { |url| url =~ MAILTO_REGEX }
+        .map { |url| URI.parse(URI.escape(url.sub(/#.*$/, ''))) }
+        .map do |uri|
+          uri.host   ||= @uri.host
+          uri.scheme ||= @uri.scheme
+          uri.to_s.sub(/\/$/, '') if external_links || uri.host =~ /#{@uri.host}$/
+        end.compact.uniq
+    end
+  end
+end

data/lib/crawlette/version.rb

@@ -0,0 +1,3 @@
+module Crawlette
+  VERSION = "0.0.1"
+end

data/spec/files/page.html

@@ -0,0 +1,209 @@
+<!doctype html>
+<!--[if IE 8]>         <html class="no-js lt-ie9" lang="en"> <![endif]-->
+<!--[if gt IE 8]><!--> <html lang="en"> <!--<![endif]-->
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <title>The UK’s #1 for online Direct Debit - GoCardless</title>
+    <meta name="description" content="GoCardless is the UK's #1 for Direct Debit, serving more companies than any other provider. Perfect for recurring billing and B2B invoicing.">
+    <meta name="viewport" content="width=device-width">
+    <meta name="og:image" content="https://gocardless.com/images/logos/gocardless-square.png">
+    <meta name="og:image:secure_url" content="https://gocardless.com/images/logos/gocardless-square.png">
+    <meta name="google-site-verification" content="Y80kah87ghJhwiDqw-5ap234p9wCcGt6kMRxvnamtHU">
+    <link href="https://plus.google.com/+Gocardless" rel="publisher">
+    <!--[if lt IE 9]>
+    <script>
+      (function() {
+        var elems = 'article aside details figcaption figure footer header hgroup main nav section summary'.split(' ');
+        var length = elems.length;
+        var index = 0;
+        for(;index < length; index++){
+          document.createElement(elems[index]);
+        }
+      })();
+    </script>
+    <![endif]-->
+    <link rel="stylesheet" href="/css/main.css">
+    <link rel="stylesheet" href="/css/fonts.css">
+  </head>
+  <body>
+
+      <script src="//cdn.optimizely.com/js/125150657.js"></script>
+
+
+    <!--[if lt IE 9]>
+      <p class="browsehappy">You are using an <strong>outdated</strong> browser.
+      Please <a href="http://browsehappy.com/">upgrade your browser</a> to improve your experience.</p>
+    <![endif]-->
+
+
+
+<div class="worry-container">
+
+  <div class="hero-worry hero-worry--girl u-center u-text-center">
+    <div class="site-container site-gutter u-cf align-btn-small u-padding-Txs u-padding-Bm">
+      <ul class="u-cf u-pull-end">
+        <li class="u-pull-start">
+          <a href="/users/sign_in/" class="btn btn--invert-hollow btn--small" id="login">Login</a>
+        </li>
+        <li class="u-pull-start u-margin-Ls">
+          <a href="/merchants/new" class="btn btn--invert-hollow btn--small" id="nav_sign_up">Sign up</a>
+        </li>
+      </ul>
+    </div>
+
+    <!-- Example video -->
+    <video src="https://pdlvimeocdn-a.akamaihd.net/45126/030/267925344.mp4"></video>
+
+    <div class="site-container">
+      <div class="grid site-gutter">
+        <div class="grid__cell u-size1of2 u-text-center u-text-heading hero-worry__heading">
+          <h1 class="u-color-invert hero-heading u-text-light">Stop worrying about online payments</h1>
+          <i class="icon-gc-logo-invert u-margin-Tm"></i>
+        </div>
+        <div class="grid__cell u-size1of2">
+          <div class="hero-worry__modal"></div>
+        </div>
+      </div>
+    </div>
+
+  </div>
+
+  <div class="u-background-white">
+    <div class="site-container u-text-center u-padding-Vl">
+
+      <div class="u-padding-Vl"><div class="u-padding-Vs">
+        <h2 class="u-text-heading u-color-meta">GoCardless makes it quick and easy to take Direct Debit</h2>
+        <div class="u-size5of12 u-center u-padding-Vm">
+          <div class="grid">
+            <div class="grid__cell u-size1of2">
+              <a href="/watch-a-demo" class="btn btn--block btn--info btn--large">Watch a demo</a>
+            </div>
+            <div class="grid__cell u-size1of2">
+              <a href="/features" class="btn btn--block btn--hollow btn--large">Learn more</a>
+            </div>
+          </div>
+        </div>
+      </div></div>
+
+      <hr class="horizontal-ruler-top-double">
+      <div class="u-padding-Vl"><div class="u-padding-Vl">
+        <i class="benefits-led-container__people-icon u-margin-Bs"></i>
+        <h1 class="u-text-heading u-text-hero u-color-primary">SIMPLE TO USE</h1>
+        <p>Sign up for free, set up in minutes. Manage everything online.</p>
+      </div></div>
+
+      <hr class="horizontal-ruler-top-double">
+      <div class="u-padding-Vl"><div class="u-padding-Vl">
+        <i class="benefits-led-container__money-icon u-margin-Bs"></i>
+        <h1 class="u-text-heading u-text-hero u-color-accent">AMAZING VALUE</h1>
+        <p>1% up to £2 with no other fees. Incredible, tailored rates for high volume.</p>
+      </div></div>
+
+      <hr class="horizontal-ruler-top-double">
+      <div class="u-padding-Vl"><div class="u-padding-Vl">
+        <i class="benefits-led-container__service-icon u-margin-Bs"></i>
+        <h1 class="u-text-heading u-text-hero u-color-secondary">LEGENDARY SERVICE</h1>
+        <p>Our personal support team are the best in the industry.</p>
+      </div></div>
+
+      <hr class="horizontal-ruler-top-double">
+      <div class="u-padding-Vl"><div class="u-padding-Vl">
+        <p class="u-margin-Bl">We've been featured in</p>
+        <div class="benefits-led-container__publications u-center"></div>
+      </div></div>
+
+      <hr class="horizontal-ruler-top-double u-margin-Vl">
+      <div class="u-padding-Vl"><div class="u-padding-Vs">
+        <p class="u-text-h2 u-text-heading u-color-meta">Get started today. <a href="/merchants/new" class="u-text-underline u-link-secondary">Sign up for free</a></p>
+      </div></div>
+    </div>
+  </div>
+</div>
+
+<div class="u-margin-Ts">
+  <div class="site-container site-gutter">
+    <div>
+  <div class="u-cf">
+    <ul class="nav u-padding-Vs u-pull-start">
+      <li class="nav__item">
+        <a href="https://help.gocardless.com#some-id">Help</a>
+      </li>
+      <li class="nav__item">
+        <a href="/contact-sales">Contact sales</a>
+      </li>
+      <li class="nav__item">
+        <a href="/faq/merchants" ng-gc-href-active>FAQ</a>
+      </li>
+      <li class="nav__item">
+        <a href="/direct-debit">Direct Debit</a>
+      </li>
+      <li class="nav__item">
+        <a href="/direct-debit/sepa/">SEPA</a>
+      </li>
+      <li class="nav__item">
+        <a href="/security" ng-gc-href-active>Security</a>
+      </li>
+      <li class="nav__item">
+        <a href="https://developer.gocardless.com">API</a>
+      </li>
+      <li class="nav__item">
+        <a href="/legal" ng-gc-href-active>Legal</a>
+      </li>
+      <li class="nav__item">
+        <a href="/about" ng-gc-href-active>About</a>
+      </li>
+      <li class="nav__item">
+        <a href="/jobs" ng-gc-href-active>Jobs</a>
+      </li>
+      <li class="nav__item">
+        <a href="/press" ng-gc-href-active>Press</a>
+      </li>
+      <li class="nav__item">
+        <a href="https://gocardless.com/blog">Blog</a>
+      </li>
+    </ul>
+    <div class="u-pull-end">
+      <a href="https://twitter.com/gocardless" class="u-margin-Ts twitter-follow-button" data-show-count="false" data-dnt="true">Follow @gocardless</a>
+      <script src="//platform.twitter.com/widgets.js" async id="twitter-wjs"></script>
+    </div>
+  </div>
+  <div class="grid u-margin-Ts">
+    <div class="u-text-h5 u-size3of12 u-padding-Vl  grid__cell">
+      <b>GoCardless Ltd</b><br>
+      338-346 Goswell Road<br>London, EC1V 7LQ<br>
+      020 7183 8674<br>
+      <a href="mailto:help@gocardless.com">help@gocardless.com</a><br>
+    </div>
+
+    <div class="u-size3of12 grid__cell u-text-h5 u-padding-Vl ">
+      <p>
+        GoCardless is regulated by the <strong>Financial Conduct
+        Authority</strong> as an Authorised Payment Institution.
+      </p>
+    </div>
+
+    <div class="grid__cell u-size6of12 u-margin-Tm u-text-end">
+      <img alt="Footer logos" class="footer__logos" src="/images/footer/footer-logos@2x.png">
+    </div>
+  </div>
+</div>
+
+  </div>
+</div>
+
+
+
+    <script src="/js/vendor.js"></script>
+    <script src="/js/main.js"></script>
+
+    <!-- Google Tag Manager -->
+    <script>
+      dataLayer = [];
+    </script>
+    <script src="//www.googletagmanager.com/gtm.js?id=GTM-PRFKNC" async></script>
+    <script>
+      (function(w,l){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});})(window, 'dataLayer');
+    </script>
+  </body>
+</html>

data/spec/files/root.html

@@ -0,0 +1,12 @@
+<!doctype html>
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <title>Fake root</title>
+    <link rel="stylesheet" href="/styles.css">
+  </head>
+  <body>
+    <a href="http://example.com/section-1"></a>
+    <a href="http://example.com/section-2"></a>
+  </body>
+</html>

data/spec/files/section-1-1.html

@@ -0,0 +1,11 @@
+<!doctype html>
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <title>Section 1-1</title>
+    <link rel="stylesheet" href="/styles.css">
+  </head>
+  <body>
+    no more links
+  </body>
+</html>

data/spec/files/section-1.html

@@ -0,0 +1,11 @@
+<!doctype html>
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <title>Section 1</title>
+    <link rel="stylesheet" href="/styles.css">
+  </head>
+  <body>
+    <a href="http://example.com/section-1-1"></a>
+  </body>
+</html>

data/spec/files/section-2.html

@@ -0,0 +1,12 @@
+<!doctype html>
+  <head>
+    <meta charset="utf-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <title>Section 2</title>
+    <link rel="stylesheet" href="/styles.css">
+  </head>
+  <body>
+    <!-- Also points to section 1.1 -->
+    <a href="http://example.com/section-1-1"></a>
+  </body>
+</html>

data/spec/lib/crawler_spec.rb

@@ -0,0 +1,40 @@
+require 'spec_helper'
+
+describe Crawlette::Crawler do
+  subject(:crawler) { Crawlette::Crawler.new('http://example.com') }
+  let(:root) { File.read('spec/files/root.html') }
+  let(:s1) { File.read('spec/files/section-1.html') }
+  let(:s2) { File.read('spec/files/section-2.html') }
+  let(:s1_1) { File.read('spec/files/section-1-1.html') }
+
+
+  describe '#crawl' do
+    before do
+      expect(Net::HTTP).to receive(:get).with(URI.parse('http://example.com')){ root }
+      expect(Net::HTTP).to receive(:get).with(URI.parse('http://example.com/section-1')){ s1 }
+      expect(Net::HTTP).to receive(:get).with(URI.parse('http://example.com/section-2')){ s2 }
+      expect(Net::HTTP).to receive(:get).with(URI.parse('http://example.com/section-1-1')).twice{ s1_1 }
+    end
+
+    it "returns a hash with the crawled urls as keys and hashes with the links and assets of each one" do
+      expect(crawler.crawl).to eq(
+        "http://example.com" => {
+          "links"=>["http://example.com/section-1", "http://example.com/section-2"],
+          "assets"=>["http://example.com/styles.css"]
+        },
+        "http://example.com/section-2"=>{
+          "links"=>["http://example.com/section-1-1"],
+          "assets"=>["http://example.com/styles.css"]
+        },
+        "http://example.com/section-1"=>{
+          "links"=>["http://example.com/section-1-1"],
+          "assets"=>["http://example.com/styles.css"]
+        },
+        "http://example.com/section-1-1"=>{
+          "links"=>[],
+          "assets"=>["http://example.com/styles.css"]
+        }
+      )
+    end
+  end
+end

data/spec/lib/page_spec.rb

@@ -0,0 +1,49 @@
+require 'spec_helper'
+
+describe Crawlette::Page do
+  subject(:page) { Crawlette::Page.new(html, URI.parse('https://gocardless.com')) }
+  let(:html) { File.read('spec/files/page.html') }
+
+  describe '#links' do
+    it "returns a unique list of normalized non-external urls" do
+      expected_links = [
+        "https://gocardless.com/users/sign_in",
+        "https://gocardless.com/merchants/new",
+        "https://gocardless.com/watch-a-demo",
+        "https://gocardless.com/features",
+        "https://help.gocardless.com",
+        "https://gocardless.com/contact-sales",
+        "https://gocardless.com/faq/merchants",
+        "https://gocardless.com/direct-debit",
+        "https://gocardless.com/direct-debit/sepa",
+        "https://gocardless.com/security",
+        "https://developer.gocardless.com",
+        "https://gocardless.com/legal",
+        "https://gocardless.com/about",
+        "https://gocardless.com/jobs",
+        "https://gocardless.com/press",
+        "https://gocardless.com/blog",
+      ]
+      expect(page.links).to match_array(expected_links)
+    end
+  end
+
+  describe '#assets' do
+    it 'returns a unique list with the normalized urls of the static assets on this page' do
+      expected_assets = [
+        "https://cdn.optimizely.com/js/125150657.js",
+        "https://pdlvimeocdn-a.akamaihd.net/45126/030/267925344.mp4",
+        "https://platform.twitter.com/widgets.js",
+        "https://gocardless.com/images/footer/footer-logos@2x.png",
+        "https://gocardless.com/js/vendor.js",
+        "https://gocardless.com/js/main.js",
+        "https://www.googletagmanager.com/gtm.js?id=GTM-PRFKNC",
+        "https://gocardless.com/css/main.css",
+        "https://gocardless.com/css/fonts.css",
+        "https://gocardless.com/images/logos/gocardless-square.png"
+      ]
+
+      expect(page.assets).to match_array(expected_assets)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,10 @@
+$LOAD_PATH << File.join(File.dirname(__FILE__), "..", "lib")
+
+require 'rspec'
+require 'crawlette'
+
+RSpec.configure do |config|
+  config.filter_run(focus: true)
+  config.run_all_when_everything_filtered = true
+  config.order = 'random'
+end

metadata

@@ -0,0 +1,143 @@
+--- !ruby/object:Gem::Specification
+name: crawlette
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Miguel Camba
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-09-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: awesome_print
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+description: Crawls a page, with no limits and without visiting external domains
+email:
+- miguel.camba@gmail.com
+executables:
+- crawlette
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/crawlette
+- crawlette.gemspec
+- lib/crawlette.rb
+- lib/crawlette/crawler.rb
+- lib/crawlette/page.rb
+- lib/crawlette/version.rb
+- spec/files/page.html
+- spec/files/root.html
+- spec/files/section-1-1.html
+- spec/files/section-1.html
+- spec/files/section-2.html
+- spec/lib/crawler_spec.rb
+- spec/lib/page_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.1
+signing_key: 
+specification_version: 4
+summary: Very simple web crawler
+test_files:
+- spec/files/page.html
+- spec/files/root.html
+- spec/files/section-1-1.html
+- spec/files/section-1.html
+- spec/files/section-2.html
+- spec/lib/crawler_spec.rb
+- spec/lib/page_spec.rb
+- spec/spec_helper.rb